© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9657
    Prev
    Next
    INDEX
    Explanations

    mentions of partnerships and cooperative efforts

    oai_token-act-pair · gemini-2.0-flash

    terms related to business partnerships

    np_token-act-pair-logits · gpt-4o-mini

    business or legal "joint" entities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rivales
    -0.45
    Jährige
    -0.44
     grunn
    -0.42
     assoluto
    -0.41
     personales
    -0.40
     negativas
    -0.40
     G
    -0.36
     rayo
    -0.36
     nervios
    -0.36
     thoáng
    -0.35
    POSITIVE LOGITS
     CreateTagHelper
    1.04
    ImageContext
    1.03
    TagMode
    0.96
    ⓧ
    0.95
    SequentialGroup
    0.93
     AssemblyCulture
    0.91
    #+#
    0.89
    :+:
    0.85
    ########.
    0.85
    CloseOperation
    0.84
    Activations Density 1.183%

    No Known Activations