© 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. 3922
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessive pronouns, especially when used to describe a person's features/expressions

    oai_token-act-pair · gemini-2.0-flash

    Faces and expressions

    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
    vician
    -0.71
    Géographie
    -0.59
     instr
    -0.55
    WireFormatLite
    -0.54
     &___
    -0.54
     createState
    -0.54
    rungsseite
    -0.53
     FED
    -0.53
     Instrument
    -0.52
    SECRET
    -0.52
    POSITIVE LOGITS
    __*/
    0.63
    HeaderText
    0.52
    InitVars
    0.52
    webElementGuid
    0.47
    /***/
    0.47
     "@/
    0.46
    ghijkl
    0.45
     useStyles
    0.43
     TestBed
    0.43
    ghijklmnop
    0.43
    Activations Density 5.259%

    No Known Activations