© 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. 14850
    Prev
    Next
    INDEX
    Explanations

    references to publication numbers

    oai_token-act-pair · gemini-2.0-flash

    single digits

    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
     שוליים
    -0.53
     himo
    -0.53
     Nine
    -0.51
     ninth
    -0.49
    ⁹
    -0.48
     Ninth
    -0.47
     SEVENTH
    -0.46
     вось
    -0.46
    ⁸
    -0.46
     九
    -0.45
    POSITIVE LOGITS
    1
    1.31
    0
    1.20
    2
    1.09
    3
    0.79
    0
    0.66
    1
    0.65
     Cæsar
    0.59
     Theſe
    0.57
    𝟎
    0.57
    Pratique
    0.57
    Activations Density 5.771%

    No Known Activations