INDEX

Explanations

mentions of isolation and leaving.

oai_token-act-pair · gemini-2.0-flash

alone

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Chham

-0.72

AnchorStyles

-0.70

帖最后由

-0.69

دانشنامهٔ

-0.68

 pinulongan

-0.66

RUnlock

-0.65

HasForeignKey

-0.65

tagHelperRunner

-0.62

MigrationBuilder

-0.61

ISupport

-0.59

POSITIVE LOGITS

自己在

0.52

endiri

0.51

自己

0.49

alone

0.49

 alone

0.48

aulted

0.47

 Alone

0.46

0.45

csol

0.45

ี่ยว

0.45

Activations Density 0.803%

mentions of isolation and leaving.

alone

No Comments

No Known Activations