© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8018
    Prev
    Next
    INDEX
    Explanations

    words used in online discussions about computers, programming, and related technical problem-solving

    oai_token-act-pair · gemini-2.0-flash

    French possessive adjectives

    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
    TagMode
    -0.63
     my
    -0.61
    VIAF
    -0.57
     autorytatywna
    -0.56
    Спасылкі
    -0.54
     CURIAM
    -0.50
     esternos
    -0.50
    featureID
    -0.49
    __(/*!
    -0.48
     mijn
    -0.47
    POSITIVE LOGITS
     ta
    1.71
     Ta
    1.27
    Ta
    1.23
     ton
    0.97
     TA
    0.91
     tes
    0.86
    Ton
    0.80
    TA
    0.71
     ma
    0.70
     TON
    0.68
    Activations Density 2.847%

    No Known Activations