© 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. 12521
    Prev
    Next
    INDEX
    Explanations

    phrases connecting two different things

    oai_token-act-pair · gemini-2.0-flash

    coding and software

    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
    וויק
    -0.56
    +#+#
    -0.49
    protoimpl
    -0.47
     hard
    -0.46
     ActivatedRoute
    -0.45
    inSlope
    -0.45
     HasFactory
    -0.45
    CASCADE
    -0.43
    Dst
    -0.43
     onlyOwner
    -0.43
    POSITIVE LOGITS
    yntaxException
    0.68
    bootstrapcdn
    0.59
    principalTable
    0.56
     digest
    0.55
    CppMethod
    0.53
     ErrInvalid
    0.53
    uxxxx
    0.53
    δυ
    0.52
    FunctionFlags
    0.52
    lectricité
    0.52
    Activations Density 0.711%

    No Known Activations