© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7022
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to installation, damage, and removal of physical objects and devices.

    oai_token-act-pair · gemini-2.0-flash

    destruction/prevention

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    __*/
    -1.20
     ExecuteAsync
    -1.13
     Roskov
    -1.03
     itſelf
    -1.02
     poffible
    -0.99
     myſelf
    -0.98
     Majefty
    -0.97
    +#+#
    -0.97
     houſe
    -0.95
    IBOutlet
    -0.95
    POSITIVE LOGITS
     id
    0.46
    ,
    0.42
     person
    0.42
    $
    0.41
    \
    0.41
     de
    0.40
     la
    0.40
     th
    0.40
     (
    0.40
     lo
    0.40
    Activations Density 4.270%

    No Known Activations