INDEX

Explanations

words related to programming, XML, personal pronouns, and generic short article words like "that" "a" "the".

oai_token-act-pair · gemini-2.0-flash

foreign languages

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

)");

-0.45

WriteBarrier

-0.43

Hochspringen

-0.42

omeness

-0.38

··

-0.33

 كومونز

-0.33

webElement

-0.33

;"></

-0.32

 forState

-0.31

<h6>

-0.31

POSITIVE LOGITS

 économiques

0.73

 Nacionales

0.70

 Generales

0.69

 religieuses

0.68

 čaj

0.68

 chrétiens

0.67

 kvinder

0.65

 conférences

0.65

 filles

0.65

 adultes

0.64

Activations Density 15.411%

words related to programming, XML, personal pronouns, and generic short article words like "that" "a" "the".

foreign languages

No Comments

No Known Activations