© 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. 8279
    Prev
    Next
    INDEX
    Explanations

    Code/mathematical language

    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
     .$
    -0.91
    $).
    -0.73
    }_{
    -0.66
    }_
    -0.66
     }_{
    -0.65
     )$
    -0.65
     _{
    -0.61
    UnusedPrivate
    -0.59
    }_{\
    -0.58
     =$
    -0.58
    POSITIVE LOGITS
    UnknownFieldSet
    0.70
    UIControlState
    0.68
    Ổ
    0.66
    ΩΝ
    0.61
    irchen
    0.60
     tambor
    0.60
    zegor
    0.59
    ỗ
    0.58
     Suffer
    0.57
    ưu
    0.56
    Activations Density 0.475%

    No Known Activations