© 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. 13217
    Prev
    Next
    INDEX
    Explanations

    sentences from a fictional story, including dialogue and descriptions, with numbers and character names

    oai_token-act-pair · gemini-2.0-flash

    end of action

    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
     pinulongan
    -0.60
    +:+
    -0.52
     Relocation
    -0.51
    webElementXpaths
    -0.47
    HideFlags
    -0.46
     unequivocal
    -0.45
     relocation
    -0.44
     jadx
    -0.44
    ('/:
    -0.43
    <!--[
    -0.43
    POSITIVE LOGITS
    ราะ
    0.56
     referenties
    0.54
    Numerade
    0.54
    ENESS
    0.53
     بيها
    0.52
    ември
    0.51
     podjela
    0.51
    ingin
    0.51
    ítulos
    0.51
     revanche
    0.51
    Activations Density 14.110%

    No Known Activations