© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12905
    Prev
    Next
    INDEX
    Explanations

    the prefix "mis-"

    oai_token-act-pair · gemini-2.0-flash

    mis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Mis
    -0.70
    stateMutability
    -0.65
     mis
    -0.63
    MigrationBuilder
    -0.60
    Datuak
    -0.59
    +#+#
    -0.59
    Mis
    -0.59
    OGND
    -0.59
    Diweddarwch
    -0.56
    mis
    -0.54
    POSITIVE LOGITS
    ſelf
    0.56
     préf
    0.50
    Παραπομπές
    0.47
    ————————————————
    0.46
     raiſ
    0.44
     altrett
    0.44
    >",
    0.44
    ppur
    0.44
     regina
    0.43
    =-=-=-=-
    0.43
    Activations Density 0.967%

    No Known Activations