INDEX

Explanations

references to actors

oai_token-act-pair · gemini-2.0-flash

actors and roles

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

 CreateTagHelper

-0.67

principalColumn

-0.60

tagHelperRunner

-0.60

رشف

-0.57

 Audiodateien

-0.56

κτή

-0.54

ividual

-0.54

CreateModel

-0.53

complexContent

-0.52

WithIOException

-0.52

POSITIVE LOGITS

interopRequire

0.67

playing

0.61

 sebagai

0.57

 playing

0.56

 thiên

0.53

Plays

0.53

 Spoilers

0.52

 ως

0.51

 plays

0.50

 jako

0.49

Activations Density 1.797%

references to actors

actors and roles

No Comments

No Known Activations