© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6397
    Prev
    Next
    INDEX
    Explanations

    measurements and product specifications, especially of screens and wheels

    oai_token-act-pair · gemini-2.0-flash

    say units of measure

    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
     an
    -0.75
    اديم
    -0.51
     BoxFit
    -0.50
     grantor
    -0.49
    KURZBESCHREIBUNG
    -0.48
    ayla
    -0.48
     trabalhadores
    -0.47
    tamia
    -0.47
    godic
    -0.45
    راض
    -0.45
    POSITIVE LOGITS
    
    0.73
    <?,
    0.57
    Билгалдахарш
    0.55
    MessageOf
    0.52
    wiſe
    0.52
     ſtate
    0.51
    €¢
    0.51
     in
    0.51
     ?</
    0.49
    ='_
    0.48
    Activations Density 9.703%

    No Known Activations