INDEX

Explanations

language describing requirements or obligations and intentions to satisfy requirements

oai_token-act-pair · gemini-2.0-flash

Rules and obligations

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

AccessorTable

-0.76

 CreateTagHelper

-0.76

contentLoaded

-0.71

 صوتيه

-0.66

Personensuche

-0.65

 незавершена

-0.65

 himo

-0.60

 Chwiliwch

-0.60

 дописавши

-0.60

 unknownFields

-0.60

POSITIVE LOGITS

 never

0.55

 always

0.54

 Always

0.52

 Never

0.49

ky

0.48

 setShow

0.48

always

0.48

never

0.47

 embodiments

0.47

 focus

0.46

Activations Density 1.488%

language describing requirements or obligations and intentions to satisfy requirements

Rules and obligations

No Comments

No Known Activations