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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12085
    Prev
    Next
    INDEX
    Explanations

    language regarding effort to avoid legal liability

    oai_token-act-pair · gemini-2.0-flash

    agreements and campaigns

    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
     effort
    -2.81
     Effort
    -2.44
    effort
    -2.42
    Effort
    -2.25
     efforts
    -1.98
     Efforts
    -1.95
    efforts
    -1.85
     attempt
    -1.80
     esfuerzo
    -1.80
     esforço
    -1.77
    POSITIVE LOGITS
     NUKAT
    0.58
    icitis
    0.52
     ComVisible
    0.50
    tinyos
    0.49
    glycemia
    0.49
     onPage
    0.49
    sidemargin
    0.48
     تضيفلها
    0.48
    ivasan
    0.47
    izziness
    0.46
    Activations Density 2.355%

    No Known Activations