© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14461
    Prev
    Next
    INDEX
    Explanations

    the indefinite article "a" followed by descriptive and evaluative adjectives, particularly in the context of expressing opinions, feelings, or making assessments.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     bit
    -0.82
     kind
    -0.67
    bit
    -0.67
    TagMode
    -0.63
     Bit
    -0.61
    kind
    -0.60
    xas
    -0.54
     sort
    -0.54
    BIT
    -0.54
    Bit
    -0.53
    POSITIVE LOGITS
     automatiques
    0.73
     africains
    0.70
     vectorielles
    0.68
     originaux
    0.65
     nationaux
    0.63
     européennes
    0.62
     secours
    0.61
     détru
    0.60
     russes
    0.60
     complètes
    0.60
    Activations Density 4.943%

    No Known Activations