© 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. 3094
    Prev
    Next
    INDEX
    Explanations

    words containing the substrings "lin", "sin", "min", and "nin"

    oai_token-act-pair · gemini-2.0-flash

    Linotype/Minardi

    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
    rungsseite
    -0.67
    s
    -0.60
    sal
    -0.59
    ی
    -0.58
    salt
    -0.58
    g
    -0.58
    t
    -0.57
    sol
    -0.57
    تقاوى
    -0.57
    e
    -0.56
    POSITIVE LOGITS
    cardia
    0.53
    chable
    0.50
    hofer
    0.49
    cator
    0.49
    culum
    0.49
    onViewCreated
    0.48
    tacts
    0.48
    hearted
    0.47
    netic
    0.47
    ecraft
    0.46
    Activations Density 4.037%

    No Known Activations