© 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. 4938
    Prev
    Next
    INDEX
    Explanations

    computer code and documentation, along with references to tables and figures, and potentially some experimental details

    oai_token-act-pair · gemini-2.0-flash

    say "S word"

    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
    s
    -2.75
     s
    -1.63
    S
    -1.52
     S
    -1.29
    sS
    -1.15
    getS
    -1.13
    Ｓ
    -1.02
    ｓ
    -1.02
    ים
    -0.98
     getS
    -0.97
    POSITIVE LOGITS
     برانيه
    0.71
    AnimationsModule
    0.68
     Normdatei
    0.53
    copg
    0.51
    ❸
    0.50
     محفوظة
    0.48
     дописавши
    0.47
     censiti
    0.47
    {~
    0.46
    ГЛА
    0.46
    Activations Density 1.837%

    No Known Activations