© 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
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 13637
    Prev
    Next
    INDEX
    Explanations

    mentions of reaching some agreement, goal, or moving towards something, often involving negotiations

    oai_token-act-pair · gemini-2.0-flash

    Reaching a goal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     reach
    -2.72
    Reach
    -2.70
     reaching
    -2.70
     Reach
    -2.67
    reach
    -2.67
     reached
    -2.64
     Reaching
    -2.63
    reached
    -2.56
     reaches
    -2.52
    Reaching
    -2.47
    POSITIVE LOGITS
    __.__
    0.44
     AssemblyTitle
    0.43
    saraba
    0.41
    олові
    0.40
     Ble
    0.39
    ols
    0.38
    outs
    0.37
    ol
    0.36
    ---|---|
    0.36
    วัติ
    0.36
    Activations Density 2.249%

    No Known Activations