INDEX

Explanations

text from Wikipedia edit histories or similar contexts, possibly names and numbers

oai_token-act-pair · gemini-2.0-flash

Incomplete/truncated article snippets

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 estiver

-0.44

BorderFactory

-0.44

 arka

-0.44

 pengusaha

-0.43

 Bezug

-0.42

buah

-0.42

 peine

-0.41

/\.

-0.41

 hennes

-0.40

 bords

-0.40

POSITIVE LOGITS

yntaxException

0.81

Tikang

0.81

 kasarigan

0.80

saraba

0.73

 ProtoMessage

0.73

 tartalomajánló

0.71

oredCriteria

0.68

 transfieras

0.65

RTEE

0.64

 estekak

0.63

Activations Density 0.979%

text from Wikipedia edit histories or similar contexts, possibly names and numbers

Incomplete/truncated article snippets

No Comments

No Known Activations