© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13171
    Prev
    Next
    INDEX
    Explanations

    first person accounts of problems with the subject telling the story and asking for help

    oai_token-act-pair · gemini-2.0-flash

    messaging or communication actions

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

    sending/contacting

    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
    tvguidetime
    -0.88
    MigrationBuilder
    -0.61
    
    -0.59
    تقاوى
    -0.50
     Laurence
    -0.48
    lear
    -0.45
     easel
    -0.45
    ANTLR
    -0.44
     يتيمه
    -0.44
    Laurence
    -0.44
    POSITIVE LOGITS
     Send
    0.65
     CONTACT
    0.63
     sent
    0.63
     SENT
    0.62
    Sent
    0.62
     Sent
    0.60
     contact
    0.60
    #+#
    0.59
    MessageTagHelper
    0.59
     sends
    0.58
    Activations Density 1.764%

    No Known Activations