© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3397
    Prev
    Next
    INDEX
    Explanations

    code, and text referring to other people's choices and emotional intelligence.

    oai_token-act-pair · gemini-2.0-flash

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     self
    -3.33
     Self
    -3.02
    Self
    -2.89
    self
    -2.83
     SELF
    -2.55
    SELF
    -2.23
     Selbst
    -2.13
     zelf
    -1.87
    Selbst
    -1.86
     selves
    -1.72
    POSITIVE LOGITS
     Clipper
    0.49
     InputDecoration
    0.49
    onin
    0.47
    addPreferredGap
    0.47
    <%=
    0.45
    gbar
    0.44
    ons
    0.42
     resultCode
    0.42
    icity
    0.41
    TagHelpers
    0.41
    Activations Density 1.889%

    No Known Activations