INDEX

Explanations

lines of code

oai_token-act-pair · gemini-2.0-flash

Code, data

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 BASED

-0.96

 based

-0.94

 Based

-0.90

Based

-0.84

based

-0.82

 تضيفلها

-0.77

expandindo

-0.76

RegressionTest

-0.75

 calendriers

-0.73

BASED

-0.72

POSITIVE LOGITS

 Mace

0.48

 exatamente

0.46

salvar

0.46

 cunning

0.45

hner

0.44

enseignement

0.44

 Cong

0.44

ESIS

0.44

 creativa

0.44

 cercana

0.44

Activations Density 1.212%

lines of code

Code, data

No Comments

No Known Activations