© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2929
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas, especially those with sub- or superscripts

    oai_token-act-pair · gemini-2.0-flash

    say "})$"

    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
    GraphicsUnit
    -0.84
    #+#
    -0.82
    новниш
    -0.79
     itſelf
    -0.74
     ſeveral
    -0.69
    Παραπομπές
    -0.68
    Personensuche
    -0.67
    Bioaccumulative
    -0.66
    '},
    
    -0.66
     мәкал
    -0.65
    POSITIVE LOGITS
    })(\
    0.58
    })-\
    0.50
    })-
    0.49
    })+
    0.47
    *,
    0.46
     O
    0.45
    })+\
    0.45
    })(
    0.44
    Ch
    0.44
    St
    0.43
    Activations Density 2.186%

    No Known Activations