© 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. 3894
    Prev
    Next
    INDEX
    Explanations

    phrases with profanity, commands, or strong opinions

    oai_token-act-pair · gemini-2.0-flash

    curse words

    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
     resourceCulture
    -0.79
    IntoConstraints
    -0.77
     الرياضيه
    -0.69
    Personendaten
    -0.69
     heck
    -0.66
     darn
    -0.65
    UnusedPrivate
    -0.65
    +#+#
    -0.64
     BrowserModule
    -0.64
     disambiguazione
    -0.63
    POSITIVE LOGITS
     f
    1.98
    f
    1.49
     F
    1.38
     fri
    1.30
    F
    1.27
     eff
    1.12
     fv
    1.02
    fri
    1.01
     getF
    1.00
     fu
    0.98
    Activations Density 3.541%

    No Known Activations