INDEX

Explanations

personal anecdotes and arguments

oai_token-act-pair · gemini-2.0-flash

reasons/explanations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 therefore

-0.69

 hence

-0.66

 поэтому

-0.65

therefore

-0.61

hence

-0.52

 donc

-0.51

PhysRev

-0.51

Aper

-0.48

ñan

-0.48

peq

-0.48

POSITIVE LOGITS

intios

0.55

ngdoc

0.55

 فريبيس

0.54

 Audiodateien

0.54

 endregion

0.53

Ibid

0.53

 समीक्षक

0.53

 SwitchCompat

0.52

 '\\;'

0.50

Morfologia

0.49

Activations Density 3.573%

personal anecdotes and arguments

reasons/explanations

No Comments

No Known Activations