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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3861
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people or groups of people who are customers, students, or members

    oai_token-act-pair · gemini-2.0-flash

    Names and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    anguages
    -0.58
     ddelweddau
    -0.51
    lang
    -0.48
     parch
    -0.47
    DropTable
    -0.46
    langs
    -0.46
    вающих
    -0.45
    ccoli
    -0.45
    virons
    -0.45
     DataFrame
    -0.44
    POSITIVE LOGITS
    migrationBuilder
    0.92
    Παραπομπές
    0.66
    simpleType
    0.65
    ConstraintMaker
    0.65
    脚注の使い方
    0.65
     ujednoznacz
    0.62
    __(/*!
    0.61
     препратки
    0.59
    elemField
    0.58
    NgModule
    0.58
    Activations Density 13.151%

    No Known Activations