INDEX

Explanations

the word "straight" and words that commonly follow it

oai_token-act-pair · gemini-2.0-flash

straight

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

GraphicsUnit

-0.66

abestanden

-0.66

 doInBackground

-0.62

ftagPool

-0.61

UnusedPrivate

-0.58

BufferException

-0.57

hoga

-0.57

 estrictamente

-0.56

unknownFields

-0.56

 AssemblyVersion

-0.56

POSITIVE LOGITS

ToAction

0.48

rück

0.47

 Skelton

0.46

Koo

0.43

readdir

0.42

 אות

0.40

lieb

0.40

Kath

0.40

الإنجليزية

0.40

Linq

0.39

Activations Density 0.588%

the word "straight" and words that commonly follow it

straight

No Comments

No Known Activations