INDEX

Explanations

the word "other" and words in the immediate vicinity like "another," "others," "anti-".

oai_token-act-pair · gemini-2.0-flash

other

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

Carriera

-0.48

الحياه

-0.45

Isle

-0.44

 zure

-0.43

Népesség

-0.43

LinkId

-0.42

ัติ

-0.41

ностран

-0.41

 Rapids

-0.41

Shea

-0.41

POSITIVE LOGITS

MENAFN

0.64

 חיצוניים

0.63

Bronnen

0.62

utilisons

0.61

(!__

0.60

indd

0.60

 calendriers

0.57

 waaronder

0.57

SizeF

0.57

ſelves

0.57

Activations Density 0.742%

the word "other" and words in the immediate vicinity like "another," "others," "anti-".

other

No Comments

No Known Activations