© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12110
    Prev
    Next
    INDEX
    Explanations

    names of prepared food dishes, with a strong bias for corn dogs and food including potatoes.

    oai_token-act-pair · gemini-2.0-flash

    food

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    مقاله
    -0.57
    ]++;
    -0.52
     ""],
    -0.52
    TargetException
    -0.51
    TagHelper
    -0.50
    ')")
    -0.50
     Bedi
    -0.50
    EObject
    -0.50
    ]--;
    -0.50
    pement
    -0.50
    POSITIVE LOGITS
     Signalez
    0.65
     disambiguazione
    0.63
     pulumi
    0.52
    KURZBESCHREIBUNG
    0.50
    rénées
    0.50
    idora
    0.48
     Exacts
    0.48
     createSprite
    0.47
     censiti
    0.45
     connues
    0.45
    Activations Density 1.084%

    No Known Activations