© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10518
    Prev
    Next
    INDEX
    Explanations

    names of people, especially when near words like "composer", "friendly", or "contemporaries"

    oai_token-act-pair · gemini-2.0-flash

    musicians and musical performances

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     notes
    -0.51
     NOTES
    -0.49
    UnsafeEnabled
    -0.47
    notes
    -0.47
     sing
    -0.46
    reme
    -0.46
    DIPSETTING
    -0.45
     maka
    -0.44
    tre
    -0.44
     bom
    -0.44
    POSITIVE LOGITS
    DockStyle
    0.75
     ostavi
    0.65
     estekak
    0.62
    Parcelize
    0.61
    rungsseite
    0.61
     كومونز
    0.61
     boucles
    0.60
     polvere
    0.59
    AnchorStyles
    0.59
    extAlignment
    0.57
    Activations Density 0.169%

    No Known Activations