© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5492
    Prev
    Next
    INDEX
    Explanations

    sentences about interpreting research data in studies

    oai_token-act-pair · gemini-2.0-flash

    interpretation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    ########.
    -0.69
    исленность
    -0.68
    InSection
    -0.65
    itinéraire
    -0.63
     switches
    -0.60
     createSprite
    -0.60
    Kariera
    -0.59
    switches
    -0.59
    switching
    -0.54
     ProtoMessage
    -0.53
    POSITIVE LOGITS
     interpretation
    1.63
     Interpretation
    1.48
     INTERPRET
    1.46
     interpreting
    1.44
    Interpretation
    1.41
     interpretations
    1.40
     interpret
    1.37
     interpreted
    1.34
     Interpret
    1.33
    interpretation
    1.32
    Activations Density 2.436%

    No Known Activations