© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3868
    Prev
    Next
    INDEX
    Explanations

    mentions of specific people, especially athletes, along with identifying rankings or exceptions.

    oai_token-act-pair · gemini-2.0-flash

    Famous people and movies

    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
     tartalomajánló
    -0.91
    SequentialGroup
    -0.84
    MigrationBuilder
    -0.63
    MemoryWarning
    -0.58
    drawal
    -0.56
     ―――――
    -0.56
    XmlAccessType
    -0.54
     doubtnut
    -0.53
     esternos
    -0.53
    athione
    -0.52
    POSITIVE LOGITS
    ēju
    0.55
     zucca
    0.50
     hábitat
    0.49
    getSelection
    0.48
     jagung
    0.44
     kucing
    0.43
     Luffy
    0.43
    ason
    0.43
     grossesse
    0.43
     Mush
    0.43
    Activations Density 2.027%

    No Known Activations