© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11397
    Prev
    Next
    INDEX
    Explanations

    code level errors

    oai_token-act-pair · gemini-2.0-flash

    error-related codes and messages

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

    Error

    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
     purpoſe
    -0.69
     reaſon
    -0.67
     itſelf
    -0.66
     RSSSF
    -0.66
     myſelf
    -0.64
     themſelves
    -0.63
     ſta
    -0.63
     juſ
    -0.57
    EndInit
    -0.56
     chofe
    -0.54
    POSITIVE LOGITS
    astify
    0.53
    AutoScaleMode
    0.48
    interceptors
    0.48
    UnknownFields
    0.47
    Données
    0.46
    Gön
    0.45
    PRWEB
    0.45
     dataSnapshot
    0.45
    mahaman
    0.44
     незавершена
    0.44
    Activations Density 2.324%

    No Known Activations