© 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. 5887
    Prev
    Next
    INDEX
    Explanations

    reviews of aftermarket car parts, especially running boards for Jeeps

    oai_token-act-pair · gemini-2.0-flash

    period/parenthesis

    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
    otene
    -0.53
     runs
    -0.52
     Running
    -0.50
     CURIAM
    -0.50
     run
    -0.49
     raw
    -0.49
     Runs
    -0.48
     Theſe
    -0.48
     best
    -0.48
    bootstrapcdn
    -0.47
    POSITIVE LOGITS
     editText
    0.56
     conflits
    0.54
     aikaa
    0.53
     yhte
    0.52
    fony
    0.50
    gency
    0.50
     setAddress
    0.49
    GIUM
    0.49
     incidente
    0.49
    aneous
    0.49
    Activations Density 4.108%

    No Known Activations