INDEX

Explanations

personal pronouns and words related to users interacting with online content or services.

oai_token-act-pair · gemini-2.0-flash

conversations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 intStringLen

-0.66

:✨

-0.66

 ModelExpression

-0.64

VIAF

-0.62

 /\.(

-0.57

 <<<<<<<<<<<<<<

-0.56

üyada

-0.53

\{\\

-0.52

 dovre

-0.52

__(/*!

-0.52

POSITIVE LOGITS

addGap

0.64

 invented

0.52

 produced

0.52

0.51

 used

0.51

 performed

0.51

 USED

0.51

 lives

0.51

Contributed

0.50

Билгалдахарш

0.49

Activations Density 1.116%

personal pronouns and words related to users interacting with online content or services.

conversations

No Comments

No Known Activations