© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12740
    Prev
    Next
    INDEX
    Explanations

    information typically found on blogs, such as ordinal numbers, dates, and common phrases such as 'published by' and 'share this'.

    oai_token-act-pair · gemini-2.0-flash

    comments and shares

    np_token-act-pair-logits · gpt-4o-mini

    Comments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    });*/
    -0.92
    queryInterface
    -0.85
    AccessorTable
    -0.82
    }*/
    -0.82
    writeFieldEnd
    -0.82
    kháu
    -0.81
    RUnlock
    -0.79
    ariConfig
    -0.77
    };*/
    -0.75
    :]:
    -0.74
    POSITIVE LOGITS
     casse
    0.40
     orec
    0.40
    なく
    0.39
     share
    0.39
    lösen
    0.38
    2
    0.38
    1
    0.38
     leave
    0.37
    好
    0.37
    去
    0.37
    Activations Density 10.350%

    No Known Activations