INDEX

Explanations

statements of evidence/research and what evidence has shown

oai_token-act-pair · gemini-2.0-flash

strong evidence

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

 المعيارى

-0.77

 nakalista

-0.77

 nahilalakip

-0.73

expandindo

-0.73

enumii

-0.73

enumi

-0.73

 Antiquities

-0.71

脚注の使い方

-0.70

InjectAttribute

-0.69

 Transfermarkt

-0.69

POSITIVE LOGITS

 evidence

1.31

 proof

1.09

evidence

1.08

 Evidence

0.96

Evidence

0.92

 EVIDENCE

0.88

proof

0.88

Proof

0.84

 evidencia

0.83

 Proof

0.81

Activations Density 2.144%

statements of evidence/research and what evidence has shown

strong evidence

No Comments

No Known Activations