© 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. 12287
    Prev
    Next
    INDEX
    Explanations

    words modifying a person's traits or actions, particularly in descriptions of characters

    oai_token-act-pair · gemini-2.0-flash

    fantasy characters

    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
    }}^{(
    -0.59
    __*/
    -0.58
     surla
    -0.54
    ^{(\
    -0.53
    }^{(\
    -0.52
     épo
    -0.51
    poptotic
    -0.50
     Leaderboard
    -0.49
     CGPA
    -0.47
    typeparam
    -0.47
    POSITIVE LOGITS
    脚注の使い方
    0.70
     يتيمه
    0.63
    CopyWith
    0.55
     Мексичка
    0.54
    iecie
    0.53
     Italijani
    0.51
    Geplaatst
    0.50
    かわらず
    0.50
    ίνεται
    0.48
     Савезне
    0.47
    Activations Density 8.148%

    No Known Activations