© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1255
    Prev
    Next
    INDEX
    Explanations

    phrases related to crashing and collisions

    oai_token-act-pair · gemini-2.0-flash

    Crash/Smash

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    Hozzáférés
    -0.68
    WebElementEntity
    -0.63
     onPostExecute
    -0.49
     surla
    -0.47
     AssemblyCulture
    -0.45
     SqlConnection
    -0.45
    الإنجليزية
    -0.44
    labus
    -0.44
    }]);
    -0.44
     morm
    -0.44
    POSITIVE LOGITS
    NameInMap
    0.73
    ThroughAttribute
    0.69
    rawDesc
    0.62
    icrous
    0.58
    phazard
    0.58
    BagLayout
    0.56
    DockStyle
    0.55
     Brother
    0.54
    mino
    0.54
    #+#
    0.52
    Activations Density 1.225%

    No Known Activations