© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5454
    Prev
    Next
    INDEX
    Explanations

    articles and words associated with discovery and problem solving

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     exact
    -0.77
     Exact
    -0.65
    exact
    -0.63
    reason
    -0.59
     reason
    -0.58
    REASON
    -0.56
     fate
    -0.56
    Exact
    -0.55
     Fate
    -0.53
    getCause
    -0.52
    POSITIVE LOGITS
     ostavi
    0.80
    AutoScaleMode
    0.70
     _$
    0.65
     propOrder
    0.61
    })*/
    0.60
    المناصب
    0.59
    fjspx
    0.59
     otomatig
    0.57
     eventdata
    0.56
     multer
    0.56
    Activations Density 9.535%

    No Known Activations