INDEX

Explanations

the numbers 0 and 1 and certain single letters, possibly in association with dates or names.

oai_token-act-pair · gemini-2.0-flash

0

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

Tally

-0.41

 množ

-0.33

 Púb

-0.32

 virtualization

-0.32

ῳ

-0.32

 marinho

-0.31

ụy

-0.31

 réguli

-0.31

 accompli

-0.31

 rapides

-0.30

POSITIVE LOGITS

findpost

0.85

исленность

0.82

)‏

0.69

\%)

0.67

 ModelExpression

0.66

interopRequire

0.65

 оригіналу

0.65

oC

0.63

ScopeManager

0.62

Lw

0.62

Activations Density 12.081%

the numbers 0 and 1 and certain single letters, possibly in association with dates or names.

0

No Comments

No Known Activations