© 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. 8117
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes and basic math equations

    oai_token-act-pair · gemini-2.0-flash

    Hexadecimal and code

    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
     poffible
    -0.77
     itſelf
    -0.76
     himſelf
    -0.76
     myſelf
    -0.75
     contextLoads
    -0.75
     themſelves
    -0.70
     يتيمه
    -0.70
     fufficient
    -0.69
     neceff
    -0.68
    ^(@)
    -0.64
    POSITIVE LOGITS
    ’).
    0.72
    ”).
    0.69
    ’
    0.64
    ).$
    0.60
     are
    0.60
    ”
    0.59
    ”),
    0.59
     },
    0.57
    ”.
    0.57
    ').
    0.56
    Activations Density 32.086%

    No Known Activations