© 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. 4892
    Prev
    Next
    INDEX
    Explanations

    quantitative comparisons and their affecting factors.

    oai_token-act-pair · gemini-2.0-flash

    factors and divisors

    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
     factor
    -2.92
     factors
    -2.86
    factors
    -2.80
     Factors
    -2.80
     Factor
    -2.75
    factor
    -2.75
    Factors
    -2.64
    Factor
    -2.59
     FACTORS
    -2.48
     FACTOR
    -2.47
    POSITIVE LOGITS
    UnsafeEnabled
    0.57
    StoryboardSegue
    0.57
    تقاوى
    0.51
     mollus
    0.49
    <?>>
    0.49
     насеље
    0.49
    rinks
    0.49
    oredCriteria
    0.48
    absl
    0.47
    bootstrapcdn
    0.47
    Activations Density 4.316%

    No Known Activations