© 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. 5345
    Prev
    Next
    INDEX
    Explanations

    text that describes a character from a sentai series.

    oai_token-act-pair · gemini-2.0-flash

    TV show plot

    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
    abetes
    -0.69
     bezeichneter
    -0.57
    IntoConstraints
    -0.55
    ]++;
    -0.52
    >`;
    -0.49
    ştır
    -0.46
    taminophen
    -0.46
    Ɓ
    -0.45
    étit
    -0.45
     незавершена
    -0.44
    POSITIVE LOGITS
    ränkt
    0.57
     Cup
    0.50
    脚注の使い方
    0.50
    bler
    0.50
     Nio
    0.49
    تفصیلات
    0.49
    examiner
    0.49
    anglicky
    0.48
    UNCIL
    0.48
    Portale
    0.47
    Activations Density 8.510%

    No Known Activations