© 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. 6630
    Prev
    Next
    INDEX
    Explanations

    capitalized prefixes, potentially names, initials, or acronyms

    oai_token-act-pair · gemini-2.0-flash

    Swaziland and "M"

    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
     متعلقه
    -0.67
    }}^{(
    -0.57
     Tart
    -0.55
    GraphicsUnit
    -0.54
    出版年
    -0.53
    rungsseite
    -0.53
     cue
    -0.52
    eroon
    -0.51
    ücks
    -0.51
    })->
    -0.51
    POSITIVE LOGITS
    Datuak
    0.59
     resourceCulture
    0.44
     handleMessage
    0.44
    ловек
    0.43
     jäsen
    0.43
    
    0.43
    bnf
    0.40
    +#+#
    0.40
    zval
    0.40
    ARGV
    0.40
    Activations Density 1.917%

    No Known Activations