INDEX

Explanations

a grab bag of common words in the English Language.

oai_token-act-pair · gemini-2.0-flash

on

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

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

IndentedString

-0.72

sizeCache

-0.65

findpost

-0.58

TableAdapter

-0.53

EDEFAULT

-0.52

tops

-0.51

 tops

-0.51

MeasureSpec

-0.49

top

-0.49

 estekak

-0.48

POSITIVE LOGITS

 referenties

0.57

on

0.57

Portail

0.56

AndEndTag

0.56

fies

0.51

nest

0.50

MessageTagHelper

0.49

 Ewig

0.48

sie

0.48

 cioccolato

0.47

Activations Density 7.333%

a grab bag of common words in the English Language.

on

No Comments

No Known Activations