© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14431
    Prev
    Next
    INDEX
    Explanations

    equations or equation references

    oai_token-act-pair · gemini-2.0-flash

    equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     betweenstory
    -0.89
     صوتيه
    -0.81
    Cuánto
    -0.75
    rrggbb
    -0.72
     FetchType
    -0.70
    Véxase
    -0.70
     GenerationType
    -0.69
     autorytatywna
    -0.66
    ratulations
    -0.66
    ükemmel
    -0.66
    POSITIVE LOGITS
    ?")
    0.60
    ?
    0.57
    ]
    0.55
    ?')
    0.53
    :')
    0.52
     *)__
    0.52
    ?]
    0.52
    ？）
    0.51
    )
    0.51
     ($)
    0.49
    Activations Density 7.555%

    No Known Activations