© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5961
    Prev
    Next
    INDEX
    Explanations

    common words like 'that' 'we' 'is' and 'the', but with no discernable pattern

    oai_token-act-pair · gemini-2.0-flash

    Problems and deficiencies

    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
     still
    -3.64
    still
    -3.44
    Still
    -3.27
     Still
    -3.23
     STILL
    -2.72
    STILL
    -2.58
     masih
    -2.23
     todavía
    -2.11
     ainda
    -2.09
     ancora
    -2.03
    POSITIVE LOGITS
    Hochspringen
    0.62
    awtextra
    0.55
     onPostExecute
    0.52
    nameof
    0.51
    AGRAM
    0.50
     duh
    0.49
    Pari
    0.49
    Bromoform
    0.48
    DropTable
    0.48
    pheny
    0.48
    Activations Density 5.169%

    No Known Activations