© 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. 7984
    Prev
    Next
    INDEX
    Explanations

    words related to appearance and evaluation

    oai_token-act-pair · gemini-2.0-flash

    sensory descriptions and opinions

    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
     صوتيه
    -0.60
     paying
    -0.60
     looking
    -0.59
     Италијани
    -0.59
     Such
    -0.59
     such
    -0.59
    disposing
    -0.58
    Paying
    -0.58
    ánto
    -0.57
    Such
    -0.57
    POSITIVE LOGITS
     &___
    0.52
     myſelf
    0.48
     ſtand
    0.47
     tranſ
    0.47
     occaf
    0.47
    Руко
    0.47
     themſelves
    0.46
     himſelf
    0.45
     uſ
    0.43
    الإنجليزية
    0.43
    Activations Density 11.069%

    No Known Activations