© 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. 13088
    Prev
    Next
    INDEX
    Explanations

    negative sentiment as signified by various dashes, quotes, and prefixes like "anti-" or "un-"

    oai_token-act-pair · gemini-2.0-flash

    Quotation marks

    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
     pleaſure
    -0.99
     purpoſe
    -0.96
     faſt
    -0.92
     houſe
    -0.91
     itſelf
    -0.90
     greateſt
    -0.90
     auffi
    -0.88
     myſelf
    -0.88
     reaſon
    -0.88
     ſind
    -0.85
    POSITIVE LOGITS
     For
    0.56
     In
    0.56
     We
    0.53
     Be
    0.51
     Not
    0.51
     One
    0.50
     My
    0.48
     As
    0.48
     Can
    0.48
     No
    0.48
    Activations Density 11.186%

    No Known Activations