© 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. 6205
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and notation

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     U
    -2.94
    U
    -2.63
     u
    -2.42
    u
    -1.84
    Ｕ
    -1.64
     У
    -1.54
    У
    -1.33
    UU
    -1.32
     UO
    -1.31
     UM
    -1.28
    POSITIVE LOGITS
     MainAxisSize
    0.50
    ainya
    0.50
    ẫy
    0.49
    ναι
    0.49
    ėms
    0.48
    ganie
    0.48
     endforeach
    0.47
    igneur
    0.46
     tắt
    0.46
    లాలు
    0.45
    Activations Density 2.429%

    No Known Activations