© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11455
    Prev
    Next
    INDEX
    Explanations

    language with quantified or measured results and/or permission and legality

    oai_token-act-pair · gemini-2.0-flash

    formal/academic texts

    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
    MigrationBuilder
    -1.33
    migrationBuilder
    -1.20
    webElementXpaths
    -1.19
    Geplaatst
    -1.17
    SourceChecksum
    -1.16
     protoimpl
    -1.14
    OGND
    -1.12
    tagHelperRunner
    -1.12
     pinulongan
    -1.11
    sizeCache
    -1.10
    POSITIVE LOGITS
     Efq
    0.02
    <bos>
    0.01
     Shakspeare
    -0.01
     Theſe
    -0.01
     itſelf
    -0.02
     photolibrary
    -0.03
     myſelf
    -0.04
     purpoſe
    -0.04
     doubtnut
    -0.04
     dreamstime
    -0.05
    Activations Density 18.952%

    No Known Activations