© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9767
    Prev
    Next
    INDEX
    Explanations

    code snippets with numbers and keywords common in code like 'ok', 'validate', 'options', and 'true'

    oai_token-act-pair · gemini-2.0-flash

    unusual syntax or formatting

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

    code and data structures

    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
    "}
    -0.84
    '}
    -0.82
    .}
    -0.74
    "},
    -0.71
    )}
    -0.70
     }
    -0.70
    }
    -0.69
    #}
    -0.68
    ?}
    -0.68
    $}
    -0.66
    POSITIVE LOGITS
    ).)
    0.57
    ogaster
    0.57
    "))
    0.57
    )))
    0.56
    '))
    0.56
    }}}{\
    0.54
     resourceCulture
    0.54
    ']));
    0.53
    "]))
    0.53
    ")))
    0.53
    Activations Density 3.712%

    No Known Activations