© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16050
    Prev
    Next
    INDEX
    Explanations

    references to how things are influenced to take a definitive stance.

    oai_token-act-pair · gemini-2.0-flash

    Specific conditions/rules

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Certain
    -1.96
     certain
    -1.91
    Certain
    -1.90
    certain
    -1.84
     CERTAIN
    -1.79
     particular
    -1.62
     tertentu
    -1.54
    particular
    -1.54
     Particular
    -1.52
     bestimmte
    -1.51
    POSITIVE LOGITS
     a
    1.28
    a
    0.64
    Kjelder
    0.45
    ａ
    0.45
     ein
    0.40
     а
    0.40
    かね
    0.38
    toni
    0.36
    väg
    0.36
    ,
    0.35
    Activations Density 2.554%

    No Known Activations