© 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. 1219
    Prev
    Next
    INDEX
    Explanations

    instances of conversational language, particularly direct speech and emotional expression.

    oai_token-act-pair · gemini-2.0-flash

    say

    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
    avigation
    -0.67
    InitVars
    -0.61
    writerow
    -0.60
    joueurs
    -0.59
    ExecuteReader
    -0.59
    WebControls
    -0.59
    Loves
    -0.59
    ImageContext
    -0.59
    RTLD
    -0.58
     سكانية
    -0.58
    POSITIVE LOGITS
    "}
    0.55
    ."'
    0.54
    .'"
    0.52
    .’”
    0.52
    ?”
    0.51
    ?"
    0.51
    "'
    0.51
    "},
    0.51
    ”?
    0.50
    Advertisement
    0.49
    Activations Density 9.355%

    No Known Activations