© 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. 6105
    Prev
    Next
    INDEX
    Explanations

    questions (mainly using the word "do")

    oai_token-act-pair · gemini-2.0-flash

    do

    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
     of
    -0.58
    MENAFN
    -0.53
     for
    -0.52
    }}_{
    -0.48
    }}_
    -0.48
    }")
    -0.47
    =").
    -0.47
    "];
    -0.46
    ']").
    -0.45
    "]).
    -0.45
    POSITIVE LOGITS
     Monfieur
    0.97
     myſelf
    0.88
     Jefus
    0.79
     Efq
    0.76
     becauſe
    0.74
     ſeveral
    0.73
     greateſt
    0.73
     purpoſe
    0.73
    DebuggerNonUser
    0.73
     themſelves
    0.73
    Activations Density 13.827%

    No Known Activations