INDEX

Explanations

job titles, and organization names.

oai_token-act-pair · gemini-2.0-flash

fields of expertise

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

govina

-0.50

itiert

-0.47

หมด

-0.46

placement

-0.45

mientras

-0.45

맡

-0.42

Cuánt

-0.42

drück

-0.42

NOWLEDG

-0.42

Биография

-0.41

POSITIVE LOGITS

GTCX

0.72

InjectAttribute

0.70

期刊论文

0.63

 متعلقه

0.63

PerformLayout

0.62

enumi

0.62

rungsseite

0.60

0.59

 defStyleAttr

0.59

+:+

0.59

Activations Density 0.687%

job titles, and organization names.

fields of expertise

No Comments

No Known Activations