© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16045
    Prev
    Next
    INDEX
    Explanations

    words and punctuation common in sports reporting, especially soccer

    oai_token-act-pair · gemini-2.0-flash

    code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    Portale
    -0.56
     whither
    -0.48
    CRF
    -0.47
    +#+#
    -0.47
     didst
    -0.46
    oprot
    -0.45
     الحره
    -0.45
     nargin
    -0.44
     Isles
    -0.44
     Objec
    -0.44
    POSITIVE LOGITS
    TagMode
    0.68
    AndEndTag
    0.61
    GOTREF
    0.59
    ekten
    0.56
     GenerationType
    0.55
    PerformLayout
    0.54
    VIOUS
    0.54
     gynhyrchwyd
    0.53
     CreateTagHelper
    0.52
     Jal
    0.51
    Activations Density 0.224%

    No Known Activations