© 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. 10377
    Prev
    Next
    INDEX
    Explanations

    words containing the character sequence "fi" or "pi"

    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
    DockStyle
    -0.82
    en
    -0.62
    ah
    -0.62
    zu
    -0.60
    final
    -0.60
    oma
    -0.60
    olo
    -0.59
    oi
    -0.58
    em
    -0.58
    ola
    -0.58
    POSITIVE LOGITS
     CURIAM
    0.53
    sailor
    0.49
     createState
    0.48
    sailing
    0.43
    égard
    0.43
    sectional
    0.43
    sunset
    0.42
    scalar
    0.42
    žně
    0.42
    salut
    0.41
    Activations Density 0.287%

    No Known Activations