© 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. 9274
    Prev
    Next
    INDEX
    Explanations

    proper nouns or adjectives

    oai_token-act-pair · 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
    __':
    -0.59
    ISupport
    -0.56
    ">//
    -0.55
    iconCls
    -0.53
     '\\;'
    -0.53
    >{@
    -0.50
     døde
    -0.47
     estekak
    -0.46
     Arhivirano
    -0.45
     /**
    -0.44
    POSITIVE LOGITS
    Rcpp
    0.53
     Walkover
    0.49
    msgTypes
    0.49
    IFICACIONES
    0.48
    letto
    0.48
    vieto
    0.47
    urbo
    0.47
     pince
    0.47
    ద్య
    0.47
    NoSuchAlgorithm
    0.47
    Activations Density 0.521%

    No Known Activations