© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12911
    Prev
    Next
    INDEX
    Explanations

    the network is looking for a wide variety of words, including past tense verbs, adjectives, and some nouns, with no clear overall meaning.

    oai_token-act-pair · gemini-2.0-flash

    Rare words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    addContainerGap
    -0.55
    ято
    -0.50
    gameserver
    -0.50
     Constitucional
    -0.46
     prisión
    -0.45
    hellip
    -0.44
     prisonniers
    -0.44
     consultato
    -0.44
    kaper
    -0.43
     Recognize
    -0.43
    POSITIVE LOGITS
     Roskov
    0.92
    RenderAtEndOf
    0.84
    #+#
    0.73
    OGND
    0.71
     protoimpl
    0.68
    transQ
    0.67
     للاسماء
    0.65
     الاطلاع
    0.65
    Jeografia
    0.60
    ########.
    0.60
    Activations Density 2.326%

    No Known Activations