© 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. 13972
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a positive opinion or quality judgement

    oai_token-act-pair · gemini-2.0-flash

    words related to being in a suitable position

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

    positions

    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
     kasarigan
    -0.88
    CPtr
    -0.66
    hoeddwyd
    -0.64
    
    -0.62
    MessageOf
    -0.62
    UpInside
    -0.60
    RenderAtEndOf
    -0.60
     Geraadpleegd
    -0.59
     ")");
    -0.59
    })->
    -0.59
    POSITIVE LOGITS
     positioned
    1.10
     equipped
    1.09
     position
    0.89
     Position
    0.84
    position
    0.83
     placed
    0.81
     fitted
    0.80
     positioning
    0.80
     POSITION
    0.78
    Position
    0.77
    Activations Density 1.910%

    No Known Activations