© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2482
    Prev
    Next
    INDEX
    Explanations

    the prepositions "with" and "on", the articles "a" and "the", possessive pronouns, verbs suggesting actions, and sometimes numbers expressing dimensions.

    oai_token-act-pair · gemini-2.0-flash

    Image context snippets

    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
    styleType
    -0.60
    =?";
    -0.55
     forState
    -0.50
    ',
    -0.50
    يرة
    -0.50
     joaat
    -0.49
    pédie
    -0.49
    ConstraintMaker
    -0.48
    ultur
    -0.48
    alami
    -0.48
    POSITIVE LOGITS
    MessageOf
    0.93
    omock
    0.67
     himo
    0.63
    Hochspringen
    0.60
     AspNetCore
    0.59
    abestanden
    0.58
    ApiModelProperty
    0.55
     opérateur
    0.54
    protoimpl
    0.53
    GMENT
    0.52
    Activations Density 1.510%

    No Known Activations