INDEX

Explanations

references to affiliation with a group, specifically the army or the union.

oai_token-act-pair · gemini-2.0-flash

legal and historical contexts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Италијани

-0.65

 '\\;'

-0.61

 AspNetCore

-0.61

ArrowToggle

-0.54

jestel

-0.54

ništ

-0.52

phology

-0.52

kháu

-0.51

AnimationsModule

-0.51

Hochspringen

-0.51

POSITIVE LOGITS

NameInMap

0.65

 oprot

0.52

tagHelperRunner

0.51

сылкі

0.50

 treo

0.50

раздо

0.48

"}")

0.47

 invokingState

0.45

modelBuilder

0.45

 Offisielt

0.45

Activations Density 1.490%

references to affiliation with a group, specifically the army or the union.

legal and historical contexts

No Comments

No Known Activations