INDEX

Explanations

words related to logic and thinking, sometimes in the context of processing trauma or emotions.

oai_token-act-pair · gemini-2.0-flash

opinions and reasoning

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 CURIAM

-0.49

webElement

-0.48

жности

-0.47

AutoresizingMask

-0.46

oog

-0.44

السكان

-0.43

 كمان

-0.42

+#+#

-0.42

 JpaRepository

-0.41

avigation

-0.41

POSITIVE LOGITS

twimg

0.70

verifyException

0.63

](#

0.58

 ());

0.57

__':

0.56

)++;

0.56

aarrggbb

0.55

makeText

0.55

oulou

0.54

Ndr

0.54

Activations Density 1.228%

words related to logic and thinking, sometimes in the context of processing trauma or emotions.

opinions and reasoning

No Known Activations