INDEX

Explanations

version numbers in software and code

oai_token-act-pair · gemini-2.0-flash

digits

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MemoryWarning

-1.16

UserScript

-1.05

########.

-1.02

EndInit

-0.96

rungsseite

-0.88

oa̍t

-0.85

AddTagHelper

-0.85

WithIOException

-0.85

 Meksiku

-0.84

AnimationsModule

-0.82

POSITIVE LOGITS

matches

0.41

 review

0.40

 depend

0.38

localctx

0.38

dek

0.38

review

0.37

fra

0.36

 оно

0.35

يال

0.35

 않습니다

0.35

Activations Density 2.785%

version numbers in software and code

digits

No Comments

No Known Activations