© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13079
    Prev
    Next
    INDEX
    Explanations

    the word "whole" or similar words connected to it

    oai_token-act-pair · gemini-2.0-flash

    whole

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     whole
    -0.47
    Y
    -0.47
    E
    -0.45
    P
    -0.44
     who
    -0.42
    G
    -0.42
    Who
    -0.42
    F
    -0.40
     difficulté
    -0.40
    The
    -0.40
    POSITIVE LOGITS
    migrationBuilder
    1.20
     disambiguazione
    1.08
     ddelweddau
    1.03
     nakalista
    0.99
    PasswordEncoder
    0.97
    StoryboardSegue
    0.96
    ftagPool
    0.94
     Normdatei
    0.94
     Numerade
    0.93
    ########.
    0.93
    Activations Density 1.682%

    No Known Activations