INDEX

Explanations

strings of numbers, often in the format of dates or journal references

oai_token-act-pair · gemini-2.0-flash

academic citations

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

 ExecuteAsync

-0.65

 للمعارف

-0.57

RTCF

-0.50

বা

-0.49

 Exactos

-0.49

 inapropiados

-0.49

CWE

-0.48

 sitter

-0.47

 חיצוניים

-0.47

 يتيمه

-0.47

POSITIVE LOGITS

kháu

0.58

TagMode

0.52

 twist

0.50

 kollu

0.49

tuesday

0.49

 neck

0.48

andar

0.47

topRight

0.47

urora

0.46

 Michelin

0.46

Activations Density 0.233%

strings of numbers, often in the format of dates or journal references

academic citations

No Comments

No Known Activations

strings of numbers, often in the format of dates or journal references

academic citations

No Comments

No Known Activations